Risk matched verification standard
Skill SylphxAI/skills/skills/risk-matched-verification-standard
Select evaluation, replay, simulation, model, and canary evidence in proportion to the actual failure model and residual uncertainty. Use when deterministic unit and integration tests cannot fully verify AI, probabilistic, distributed, concurrent, or time-dependent behavior. Use CI Admission for flaky-check attribution or quarantine; do not add expensive verification machinery to an ordinary deterministic code path.From its SKILL.md
npx -y skills add SylphxAI/skills --skill risk-matched-verification-standardAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- 22 days oldThe repository was created 22 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
- 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
SKILL.md
2.0 KB, 297 tokens by cl100k_base, as published. Nobody here has run it
Risk-Matched Verification Standard
Requirement: apply this standard when the task matches its scope.
Read references/full-standard.md for the full method and predicates.
Focused methods:
Method
- Read references/full-standard.md for the full method and predicates.
- Apply the strongest relevant subset; record material tradeoffs in ADR/tests as required.
- Prefer schema/test/ADR homes over copying this body into product repos.
Composition and output
Apply this standard as constraints on the artifact requested by the user or owned by the primary procedure. Do not emit a separate per-standard compliance report merely because this Skill was injected.
Integrate only material obligations, deviations, evidence, and gaps into the primary artifact or final status. When conformance assessment is itself the requested job, produce one standalone domain conformance record from this standard.
Boundaries
- Does not grant deploy, credential, or MCP capabilities.
- Does not replace product-local ADRs where those own decisions.
When not to use
- Product-specific live coordination operations → the matching adapter Skill and that product's current API or tool schema.
- Unrelated commercial packaging alone → commercial-decision-standard when in scope.
What ships with it: 2 files
12.1 KB alongside SKILL.md
agents/
- openai.yaml277 B
references/
- full-standard.md11.8 KB